Add a statistics pane to the webhook page (closes #368)

Each webhook's event database keeps one row of running totals: events,
deliveries and failures, and how many of each retention removed.
Storing an event, creating a delivery, a delivery becoming failed and
the retention sweep each update it in the transaction that writes or
deletes the rows it counts. Deliveries get a finished_at column, the
last column of the status index, so the last-10-minutes and
last-24-hours figures are index-range counts. The pane is its own
template, included at the top of the page.

The schema changes in place with nothing back-filled, so an existing
database must be recreated.

Model: opus-5-5

internal/handlers/delivery_replay.go

@@ -299,7 +299,8 @@ func countInFlightDeliveries(
 	return count, err
 }
 
-// createReplayDelivery writes the new pending delivery row and returns
+// createReplayDelivery writes the new pending delivery row, adds it to
+// the webhook's running totals in the same transaction, and returns
 // the task that carries it to the delivery engine.
 //
 // The row is written with associations omitted, and neither Event nor
@@ -319,7 +320,14 @@ func createReplayDelivery(
 		Status:   database.DeliveryStatusPending,
 	}
 
-	err := webhookDB.Omit(clause.Associations).Create(dlv).Error
+	err := webhookDB.Transaction(func(tx *gorm.DB) error {
+		err := tx.Omit(clause.Associations).Create(dlv).Error
+		if err != nil {
+			return err
+		}
+
+		return database.AddTotals(tx, database.Totals{Deliveries: 1})
+	})
 	if err != nil {
 		return delivery.Task{}, err
 	}

internal/handlers/export_test.go

@@ -69,6 +69,21 @@ func (s *Handlers) LoadEventLogViewsForTest(
 	return views
 }
 
+// WebhookStatsForTest returns the figures the statistics pane on a
+// webhook's page shows, from the webhook's entrypoints and targets
+// loaded as that page loads them.
+func (s *Handlers) WebhookStatsForTest(webhookID string) *WebhookStats {
+	var entrypoints []database.Entrypoint
+
+	s.db.DB().Where("webhook_id = ?", webhookID).Find(&entrypoints)
+
+	var targets []database.Target
+
+	s.db.DB().Where("webhook_id = ?", webhookID).Find(&targets)
+
+	return s.loadWebhookStats(webhookID, entrypoints, targets)
+}
+
 // AddTemplateForTest registers a template under a page name so that
 // the handlers_test package can drive the render path with a
 // template of its own.

internal/handlers/handlers.go

@@ -91,18 +91,22 @@ type Handlers struct {
 
 // parsePageTemplate parses a page-specific template set from the
 // embedded FS. Each page template is combined with the shared
-// base, htmlheader, and navbar templates. The page file must be
-// listed first so that its root action ({{template "base" .}})
-// becomes the template set's entry point.
-func parsePageTemplate(pageFile string) *template.Template {
+// base, htmlheader, and navbar templates, and with any further files
+// the page includes. The page file must be listed first so that its
+// root action ({{template "base" .}}) becomes the template set's entry
+// point.
+func parsePageTemplate(
+	pageFile string, included ...string,
+) *template.Template {
+	files := append([]string{
+		pageFile,
+		"base.html",
+		"htmlheader.html",
+		"navbar.html",
+	}, included...)
+
 	return template.Must(
-		template.ParseFS(
-			templates.Templates,
-			pageFile,
-			"base.html",
-			"htmlheader.html",
-			"navbar.html",
-		),
+		template.ParseFS(templates.Templates, files...),
 	)
 }
 
@@ -131,7 +135,7 @@ func New(
 		"profile.html":       parsePageTemplate("profile.html"),
 		"sources_list.html":  parsePageTemplate("sources_list.html"),
 		"sources_new.html":   parsePageTemplate("sources_new.html"),
-		"source_detail.html": parsePageTemplate("source_detail.html"),
+		"source_detail.html": parsePageTemplate("source_detail.html", "webhook_stats.html"),
 		"source_edit.html":   parsePageTemplate("source_edit.html"),
 		"source_logs.html":   parsePageTemplate("source_logs.html"),
 		"target_edit.html":   parsePageTemplate("target_edit.html"),

internal/handlers/source_management.go

@@ -450,6 +450,7 @@ func (h *Handlers) renderSourceDetail(
 		"Targets":     delivery.NewTargetViews(targets),
 		"Events":      events,
 		"BaseURL":     baseURL,
+		"Stats":       h.loadWebhookStats(webhook.ID, entrypoints, targets),
 	}
 
 	h.renderTemplate(w, r, "source_detail.html", data)

internal/handlers/webhook.go

@@ -252,11 +252,12 @@ func requestEventSource(
 	}
 }
 
-// createAndFanOut writes the event and one pending delivery per target
-// in a single transaction, then hands the tasks to the delivery
-// engine. It is the only path by which an event and its deliveries are
-// created, so a resubmitted event is retried, SSRF-guarded and
-// circuit-broken exactly as a received one is.
+// createAndFanOut writes the event and one pending delivery per target,
+// and adds them to the webhook's running totals, in a single
+// transaction, then hands the tasks to the delivery engine. It is the
+// only path by which an event and its deliveries are created, so a
+// resubmitted event is retried, SSRF-guarded and circuit-broken
+// exactly as a received one is.
 //
 // The tasks are returned as well as queued, so a caller can report how
 // many targets the event went to.
@@ -296,6 +297,16 @@ func (h *Handlers) createAndFanOut(
 		return nil, nil, err
 	}
 
+	err = database.AddTotals(tx, database.Totals{
+		Events:     1,
+		Deliveries: int64(len(tasks)),
+	})
+	if err != nil {
+		tx.Rollback()
+
+		return nil, nil, err
+	}
+
 	err = tx.Commit().Error
 	if err != nil {
 		return nil, nil, fmt.Errorf(

internal/handlers/webhook_stats.go

@@ -0,0 +1,211 @@
+package handlers
+
+import (
+	"fmt"
+	"time"
+
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// The spans of the two recent windows the statistics pane reports on.
+const (
+	tenMinutes      = 10 * time.Minute
+	twentyFourHours = 24 * time.Hour
+)
+
+// percent turns a fraction into a percentage.
+const percent = 100
+
+// WebhookStats holds the figures in the statistics pane at the top of
+// the webhook page.
+type WebhookStats struct {
+	Entrypoints       int
+	ActiveEntrypoints int
+	Targets           int
+	ActiveTargets     int
+
+	// Totals holds the lifetime counts of events, deliveries and
+	// failures, and how many of each retention has removed.
+	Totals database.Totals
+
+	// InProgress counts the deliveries still pending or retrying.
+	InProgress int64
+
+	// LastEventAt is when the newest stored event arrived, or nil when
+	// none is stored.
+	LastEventAt *time.Time
+
+	Last10Minutes RecentWindow
+	Last24Hours   RecentWindow
+}
+
+// RecentWindow holds what happened in one recent window: the events
+// received in it, and the deliveries that became delivered or failed in
+// it.
+type RecentWindow struct {
+	Events    int64
+	Delivered int64
+	Failed    int64
+}
+
+// FailurePercent is the share of the deliveries finished in the window
+// that failed, or a dash when none finished. Deliveries still pending
+// or retrying are not counted either way.
+func (w RecentWindow) FailurePercent() string {
+	finished := w.Delivered + w.Failed
+	if finished == 0 {
+		return "—"
+	}
+
+	return fmt.Sprintf(
+		"%.1f%%", percent*float64(w.Failed)/float64(finished),
+	)
+}
+
+// loadWebhookStats gathers the figures for the statistics pane from the
+// webhook's entrypoints and targets, as the page has already loaded
+// them, and from its event database. It returns nil, and logs why, when
+// the event database cannot be read.
+func (h *Handlers) loadWebhookStats(
+	webhookID string,
+	entrypoints []database.Entrypoint,
+	targets []database.Target,
+) *WebhookStats {
+	stats := &WebhookStats{
+		Entrypoints: len(entrypoints),
+		Targets:     len(targets),
+	}
+
+	for i := range entrypoints {
+		if entrypoints[i].Active {
+			stats.ActiveEntrypoints++
+		}
+	}
+
+	for i := range targets {
+		if targets[i].Active {
+			stats.ActiveTargets++
+		}
+	}
+
+	// Opening an event database that does not exist would create it,
+	// and it would hold nothing to count.
+	if !h.dbMgr.DBExists(webhookID) {
+		return stats
+	}
+
+	webhookDB, err := h.dbMgr.GetDB(webhookID)
+	if err == nil {
+		err = readEventStats(webhookDB, time.Now(), stats)
+	}
+
+	if err != nil {
+		h.log.Error(
+			"failed to read webhook statistics",
+			"webhook_id", webhookID,
+			"error", err,
+		)
+
+		return nil
+	}
+
+	return stats
+}
+
+// readEventStats fills in the figures that come from the webhook's
+// event database. None of them reads every stored row: the totals are
+// one row, and every other figure is read from an index, over only the
+// rows it counts.
+func readEventStats(
+	db *gorm.DB, now time.Time, stats *WebhookStats,
+) error {
+	err := db.Take(&stats.Totals).Error
+	if err != nil {
+		return fmt.Errorf("reading running totals: %w", err)
+	}
+
+	err = db.Model(&database.Delivery{}).
+		Where("status IN ?", []database.DeliveryStatus{
+			database.DeliveryStatusPending,
+			database.DeliveryStatusRetrying,
+		}).
+		Count(&stats.InProgress).Error
+	if err != nil {
+		return fmt.Errorf("counting deliveries in progress: %w", err)
+	}
+
+	var newest []time.Time
+
+	err = db.Model(&database.Event{}).
+		Order("created_at DESC").
+		Limit(1).
+		Pluck("created_at", &newest).Error
+	if err != nil {
+		return fmt.Errorf("reading newest event time: %w", err)
+	}
+
+	if len(newest) > 0 {
+		stats.LastEventAt = &newest[0]
+	}
+
+	stats.Last10Minutes, err = readRecentWindow(
+		db, now.Add(-tenMinutes),
+	)
+	if err != nil {
+		return err
+	}
+
+	stats.Last24Hours, err = readRecentWindow(
+		db, now.Add(-twentyFourHours),
+	)
+
+	return err
+}
+
+// readRecentWindow counts the events received, and the deliveries that
+// became delivered or failed, since the given time.
+func readRecentWindow(
+	db *gorm.DB, since time.Time,
+) (RecentWindow, error) {
+	var w RecentWindow
+
+	err := db.Model(&database.Event{}).
+		Where("created_at >= ?", since).
+		Count(&w.Events).Error
+	if err != nil {
+		return w, fmt.Errorf("counting recent events: %w", err)
+	}
+
+	w.Delivered, err = countFinishedSince(
+		db, database.DeliveryStatusDelivered, since,
+	)
+	if err != nil {
+		return w, err
+	}
+
+	w.Failed, err = countFinishedSince(
+		db, database.DeliveryStatusFailed, since,
+	)
+
+	return w, err
+}
+
+// countFinishedSince counts the deliveries that reached the given
+// final status since the given time.
+func countFinishedSince(
+	db *gorm.DB, status database.DeliveryStatus, since time.Time,
+) (int64, error) {
+	var n int64
+
+	err := db.Model(&database.Delivery{}).
+		Where("status = ? AND finished_at >= ?", status, since).
+		Count(&n).Error
+	if err != nil {
+		return 0, fmt.Errorf(
+			"counting deliveries %s recently: %w", status, err,
+		)
+	}
+
+	return n, nil
+}

internal/handlers/webhook_stats_test.go

@@ -0,0 +1,331 @@
+package handlers_test
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/go-chi/chi"
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"go.uber.org/fx/fxtest"
+	"gorm.io/gorm"
+	"gorm.io/gorm/clause"
+	"sneak.berlin/go/webhooker/internal/config"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/handlers"
+	"sneak.berlin/go/webhooker/internal/logger"
+	"sneak.berlin/go/webhooker/internal/session"
+)
+
+// statsReceive posts one event to an entrypoint through the real
+// receiver.
+func statsReceive(t *testing.T, h *handlers.Handlers, path string) {
+	t.Helper()
+
+	req := httptest.NewRequestWithContext(
+		context.Background(), http.MethodPost, "/",
+		strings.NewReader(`{"stats":true}`),
+	)
+
+	rctx := chi.NewRouteContext()
+	rctx.URLParams.Add("uuid", path)
+
+	req = req.WithContext(context.WithValue(
+		req.Context(), chi.RouteCtxKey, rctx,
+	))
+
+	w := httptest.NewRecorder()
+	h.HandleWebhook().ServeHTTP(w, req)
+
+	require.Equal(t, http.StatusOK, w.Code)
+}
+
+// statsEntrypoint adds an entrypoint to a webhook and returns its path.
+func statsEntrypoint(
+	t *testing.T, db *database.Database, webhookID string, active bool,
+) string {
+	t.Helper()
+
+	ep := &database.Entrypoint{
+		WebhookID: webhookID,
+		Path:      uuid.New().String(),
+	}
+
+	require.NoError(t, db.DB().Omit(clause.Associations).Create(ep).Error)
+	require.NoError(t, db.DB().Model(ep).Update("active", active).Error)
+
+	return ep.Path
+}
+
+// statsDelivery returns the id of an event's delivery to a target.
+func statsDelivery(
+	t *testing.T, webhookDB *gorm.DB, eventID, targetID string,
+) string {
+	t.Helper()
+
+	var d database.Delivery
+
+	require.NoError(t, webhookDB.Where(
+		"event_id = ? AND target_id = ?", eventID, targetID,
+	).First(&d).Error)
+
+	return d.ID
+}
+
+// statsFinish settles a delivery as the delivery engine does: its
+// final status and the time it finished, and for a failure one more on
+// the webhook's failure total, in one transaction.
+func statsFinish(
+	t *testing.T,
+	webhookDB *gorm.DB,
+	deliveryID string,
+	status database.DeliveryStatus,
+	at time.Time,
+) {
+	t.Helper()
+
+	require.NoError(t, webhookDB.Transaction(func(tx *gorm.DB) error {
+		err := tx.Model(&database.Delivery{}).
+			Where("id = ?", deliveryID).
+			Updates(map[string]any{"status": status, "finished_at": at}).
+			Error
+		if err != nil || status != database.DeliveryStatusFailed {
+			return err
+		}
+
+		return database.AddTotals(tx, database.Totals{Failures: 1})
+	}))
+}
+
+// statsAge moves an event's arrival back to the given time.
+func statsAge(
+	t *testing.T, webhookDB *gorm.DB, eventID string, at time.Time,
+) {
+	t.Helper()
+
+	require.NoError(t, webhookDB.Model(&database.Event{}).
+		Where("id = ?", eventID).
+		Update("created_at", at).Error)
+}
+
+// statsPrune runs the real retention reaper until it has removed one
+// event from the webhook's database, then stops it.
+func statsPrune(
+	t *testing.T,
+	db *database.Database,
+	dbMgr *database.WebhookDBManager,
+	log *logger.Logger,
+	webhookDB *gorm.DB,
+) {
+	t.Helper()
+
+	lc := fxtest.NewLifecycle(t)
+	database.NewRetentionReaper(lc, database.RetentionReaperParams{
+		Config: &config.Config{
+			RetentionSweepInterval: 10 * time.Millisecond,
+		},
+		Database:  db,
+		DBManager: dbMgr,
+		Logger:    log,
+	})
+
+	lc.RequireStart()
+
+	require.Eventually(t, func() bool {
+		var totals database.Totals
+
+		err := webhookDB.Take(&totals).Error
+
+		return err == nil && totals.EventsRemoved == 1
+	}, 10*time.Second, 10*time.Millisecond)
+
+	lc.RequireStop()
+}
+
+// assertStatsTotals checks the lifetime events, deliveries and
+// failures, and those within retention.
+func assertStatsTotals(
+	t *testing.T, totals database.Totals, lifetime, within [3]int64,
+) {
+	t.Helper()
+
+	assert.Equal(t, lifetime, [3]int64{
+		totals.Events, totals.Deliveries, totals.Failures,
+	}, "lifetime events, deliveries, failures")
+	assert.Equal(t, within, [3]int64{
+		totals.EventsWithinRetention(),
+		totals.DeliveriesWithinRetention(),
+		totals.FailuresWithinRetention(),
+	}, "events, deliveries, failures within retention")
+}
+
+// TestWebhookStats_EveryFigureAcrossRetentionPrune builds a webhook's
+// history through the receiver and a replay, settles its deliveries as
+// the delivery engine would, and checks every figure the statistics
+// pane shows, before and after the real retention reaper removes the
+// oldest event.
+func TestWebhookStats_EveryFigureAcrossRetentionPrune(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+		log   *logger.Logger
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &log)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := &database.Webhook{
+		UserID: deleteTestUserID, Name: "stats", RetentionDays: 1,
+	}
+	require.NoError(t, db.DB().Omit(clause.Associations).Create(wh).Error)
+
+	path := statsEntrypoint(t, db, wh.ID, true)
+	statsEntrypoint(t, db, wh.ID, false)
+
+	first := seedConfiguredTarget(
+		t, db, wh.ID, database.TargetTypeHTTP,
+		`{"url":"`+replayTargetURL+`"}`,
+	)
+	second := seedTarget(t, db, wh.ID, database.TargetTypeLog)
+	inactive := seedTarget(t, db, wh.ID, database.TargetTypeLog)
+	require.NoError(t, db.DB().Model(inactive).
+		Update("active", false).Error)
+
+	// Three events, each delivered to the two active targets.
+	for range 3 {
+		statsReceive(t, h, path)
+	}
+
+	webhookDB, err := dbMgr.GetDB(wh.ID)
+	require.NoError(t, err)
+
+	events := listEvents(t, webhookDB)
+	require.Len(t, events, 3)
+
+	oldest, middle, newest := events[0], events[1], events[2]
+	now := time.Now()
+
+	// The oldest is past the webhook's one day of retention.
+	statsAge(t, webhookDB, oldest.ID, now.Add(-50*time.Hour))
+	statsAge(t, webhookDB, middle.ID, now.Add(-6*time.Hour))
+
+	oldestFailure := statsDelivery(t, webhookDB, oldest.ID, first.ID)
+	statsFinish(t, webhookDB, oldestFailure,
+		database.DeliveryStatusFailed, now.Add(-49*time.Hour))
+	statsFinish(t, webhookDB,
+		statsDelivery(t, webhookDB, oldest.ID, second.ID),
+		database.DeliveryStatusDelivered, now.Add(-49*time.Hour))
+	statsFinish(t, webhookDB,
+		statsDelivery(t, webhookDB, middle.ID, first.ID),
+		database.DeliveryStatusFailed, now.Add(-5*time.Hour))
+	statsFinish(t, webhookDB,
+		statsDelivery(t, webhookDB, middle.ID, second.ID),
+		database.DeliveryStatusFailed, now.Add(-time.Minute))
+	statsFinish(t, webhookDB,
+		statsDelivery(t, webhookDB, newest.ID, first.ID),
+		database.DeliveryStatusDelivered, now.Add(-2*time.Minute))
+
+	// A replay adds a delivery, still pending, to the oldest event.
+	require.Equal(t, http.StatusSeeOther,
+		postReplay(t, h, sess, wh.ID, oldestFailure).Code)
+
+	stats := h.WebhookStatsForTest(wh.ID)
+	require.NotNil(t, stats)
+
+	assert.Equal(t, 2, stats.Entrypoints)
+	assert.Equal(t, 1, stats.ActiveEntrypoints)
+	assert.Equal(t, 3, stats.Targets)
+	assert.Equal(t, 2, stats.ActiveTargets)
+	assertStatsTotals(t, stats.Totals, [3]int64{3, 7, 3}, [3]int64{3, 7, 3})
+	assert.Equal(t, int64(2), stats.InProgress)
+	require.NotNil(t, stats.LastEventAt)
+	assert.True(t, newest.CreatedAt.Equal(*stats.LastEventAt))
+	assert.Equal(t, handlers.RecentWindow{
+		Events: 1, Delivered: 1, Failed: 1,
+	}, stats.Last10Minutes)
+	assert.Equal(t, handlers.RecentWindow{
+		Events: 2, Delivered: 1, Failed: 2,
+	}, stats.Last24Hours)
+	assert.Equal(t, "50.0%", stats.Last10Minutes.FailurePercent())
+	assert.Equal(t, "66.7%", stats.Last24Hours.FailurePercent())
+
+	// Retention removes the oldest event with its three deliveries,
+	// one of them failed and one the pending replay.
+	statsPrune(t, db, dbMgr, log, webhookDB)
+
+	after := h.WebhookStatsForTest(wh.ID)
+	require.NotNil(t, after)
+
+	assertStatsTotals(t, after.Totals, [3]int64{3, 7, 3}, [3]int64{2, 4, 2})
+	assert.Equal(t, int64(1), after.InProgress)
+	assert.Equal(t, stats.LastEventAt, after.LastEventAt)
+	assert.Equal(t, stats.Last10Minutes, after.Last10Minutes)
+	assert.Equal(t, stats.Last24Hours, after.Last24Hours)
+
+	body := renderSourceDetailPage(t, h, sess, wh.ID)
+	assert.Contains(t, body, "Statistics")
+	assert.Contains(t, body, "Within retention")
+	assert.Contains(t, body, "50.0%")
+	assert.Contains(t, body, "66.7%")
+}
+
+// TestWebhookStats_WebhookWithNoEvents covers a webhook whose event
+// database has never been opened: every count is zero, the
+// percentages are a dash, and showing the page does not create the
+// database.
+func TestWebhookStats_WebhookWithNoEvents(t *testing.T) {
+	t.Parallel()
+
+	var (
+		h     *handlers.Handlers
+		sess  *session.Session
+		db    *database.Database
+		dbMgr *database.WebhookDBManager
+	)
+
+	app := newTestApp(t, &h, &sess, &db, &dbMgr)
+	app.RequireStart()
+
+	t.Cleanup(app.RequireStop)
+
+	wh := seedWebhook(t, db)
+
+	assert.Equal(t, &handlers.WebhookStats{}, h.WebhookStatsForTest(wh.ID))
+	assert.Equal(t, "—", handlers.RecentWindow{}.FailurePercent())
+
+	body := renderSourceDetailPage(t, h, sess, wh.ID)
+	assert.Contains(t, body, "Statistics")
+	assert.False(t, dbMgr.DBExists(wh.ID))
+}
+
+// TestRecentWindow_FailurePercent pins the percentage: failed
+// deliveries out of all that finished in the window.
+func TestRecentWindow_FailurePercent(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		window handlers.RecentWindow
+		want   string
+	}{
+		{handlers.RecentWindow{}, "—"},
+		{handlers.RecentWindow{Events: 4}, "—"},
+		{handlers.RecentWindow{Delivered: 3, Failed: 1}, "25.0%"},
+		{handlers.RecentWindow{Failed: 2}, "100.0%"},
+		{handlers.RecentWindow{Delivered: 2}, "0.0%"},
+	}
+
+	for _, tt := range tests {
+		assert.Equal(t, tt.want, tt.window.FailurePercent(), tt.window)
+	}
+}